Model comparison
Llama 3.2 90B vs Olmo 3.1 32b Instruct
Olmo 3.1 32b Instruct is the stronger model overall, scoring 38.8 to 27.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- The widest gap is in math, where Olmo 3.1 32b Instruct leads 33.6 to 10.4.
Side by side
| Llama 3.2 90B | Olmo 3.1 32b Instruct | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 27.1 | 38.8 |
| Released | 2024-09-24 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Olmo 3.1 32b Instruct: 38.9 (#154)
| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Coding | — | 1346 |
Agentic & Tool Use Not comparable
Llama 3.2 90B: 29.7 (#73), Olmo 3.1 32b Instruct: —
| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| BALROG | 27.3% | — |
Reasoning Olmo 3.1 32b Instruct leads
Llama 3.2 90B: 20.9 (#207), Olmo 3.1 32b Instruct: 25.4 (#131)
| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1322 |
| Epoch Capabilities Index | 125.5 | — |
Math Olmo 3.1 32b Instruct leads
Llama 3.2 90B: 10.4 (#302), Olmo 3.1 32b Instruct: 33.6 (#169)
| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| LMArena Math | — | 1305 |
| MATH Level 5 | 39.4% | — |
Knowledge Olmo 3.1 32b Instruct leads
Llama 3.2 90B: 21.7 (#269), Olmo 3.1 32b Instruct: 35.4 (#175)
| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| GPQA Diamond | 41% | — |
| LMArena Expert | — | 1307 |
| MMLU | 80.3% | — |
Multimodal Not comparable
Llama 3.2 90B: 24.9 (#119), Olmo 3.1 32b Instruct: —
| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Multilingual Not comparable
Llama 3.2 90B: —, Olmo 3.1 32b Instruct: 42.8 (#185)
| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Non-English | — | 1275 |
| LMArena Chinese | — | 1304 |
| LMArena French | — | 1328 |
| LMArena German | — | 1283 |
| LMArena Korean | — | 1206 |
| LMArena Russian | — | 1268 |
| LMArena Spanish | — | 1337 |
Instruction Following Not comparable
Llama 3.2 90B: —, Olmo 3.1 32b Instruct: 68.8 (#182)
| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1298 |
Long Context Not comparable
Llama 3.2 90B: —, Olmo 3.1 32b Instruct: 39.9 (#161)
| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1312 |
Writing & Preference Not comparable
Llama 3.2 90B: —, Olmo 3.1 32b Instruct: 50.4 (#179)
| Benchmark | Llama 3.2 90B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Text | — | 1311 |
| LMArena Creative Writing | — | 1264 |
| LMArena Multi-Turn | — | 1309 |
Frequently asked questions
Is Llama 3.2 90B better than Olmo 3.1 32b Instruct?
Olmo 3.1 32b Instruct is the stronger model overall, scoring 38.8 to 27.1 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Olmo 3.1 32b Instruct share?
0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Olmo 3.1 32b Instruct has 16.